How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("diffusers/consistency-models-test", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

These UNet2DModel checkpoints are small randomly-initialized U-Nets which accept 32x32 images for use in testing consistency models. "test_unet_class_cond" is class-conditional (e.g. contains a class label embedding), while "test_unet" is not. Please refer to the original model card for more information about consistency models.

Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support